Spaces:
Build error
Build error
Upload app.py
Browse files
app.py
CHANGED
@@ -11,9 +11,10 @@ from wordcloud import WordCloud, STOPWORDS
|
|
11 |
from nltk.corpus import stopwords
|
12 |
import datasets
|
13 |
from datasets import load_dataset
|
|
|
14 |
import sklearn
|
15 |
from sklearn.preprocessing import LabelEncoder
|
16 |
-
|
17 |
# loading dataset
|
18 |
dataset = load_dataset("merve/poetry", streaming=True)
|
19 |
df = pd.DataFrame.from_dict(dataset["train"])
|
@@ -36,30 +37,46 @@ df.content = df.content.apply(lambda x: ' '.join([word for word in x.split() if
|
|
36 |
df.content=df.content.apply(standardize)
|
37 |
st.dataframe(df)
|
38 |
|
39 |
-
|
40 |
-
st.write("Most appearing words including stopwords")
|
41 |
-
words = df.content.str.split(expand=True).unstack().value_counts()
|
42 |
-
st.bar_chart(words[0:50])
|
43 |
-
st.set_option('deprecation.showPyplotGlobalUse', False)
|
44 |
|
|
|
|
|
|
|
|
|
45 |
|
|
|
|
|
|
|
|
|
46 |
|
47 |
-
|
|
|
|
|
|
|
48 |
|
49 |
# distributions of poem types according to ages and authors
|
50 |
-
st.write("Distributions of poem types according to ages and authors
|
|
|
|
|
51 |
le = LabelEncoder()
|
52 |
|
53 |
df.author = le.fit_transform(df.author)
|
54 |
sns.catplot(x="age", y="author",hue="type", data=df)
|
55 |
st.pyplot()
|
56 |
|
|
|
|
|
57 |
# most appearing words other than stop words
|
58 |
-
|
|
|
|
|
|
|
|
|
|
|
59 |
import matplotlib.pyplot as plt
|
60 |
def word_cloud(content, title):
|
61 |
wc = WordCloud(background_color="white", max_words=200,contour_width=3,
|
62 |
-
stopwords=STOPWORDS,
|
63 |
wc.generate(" ".join(content.index.values))
|
64 |
fig = plt.figure(figsize=(10, 10))
|
65 |
plt.title(title, fontsize=20)
|
@@ -67,5 +84,12 @@ def word_cloud(content, title):
|
|
67 |
plt.axis('off')
|
68 |
st.pyplot()
|
69 |
|
70 |
-
st.
|
71 |
-
word_cloud(
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
from nltk.corpus import stopwords
|
12 |
import datasets
|
13 |
from datasets import load_dataset
|
14 |
+
import matplotlib.pyplot as plt
|
15 |
import sklearn
|
16 |
from sklearn.preprocessing import LabelEncoder
|
17 |
+
sns.set_palette("RdBu")
|
18 |
# loading dataset
|
19 |
dataset = load_dataset("merve/poetry", streaming=True)
|
20 |
df = pd.DataFrame.from_dict(dataset["train"])
|
|
|
37 |
df.content=df.content.apply(standardize)
|
38 |
st.dataframe(df)
|
39 |
|
40 |
+
st.subheader("Visualization on dataset statistics")
|
|
|
|
|
|
|
|
|
41 |
|
42 |
+
st.write("Number of poems written in each type")
|
43 |
+
sns.catplot(x="type", data=df, kind="count")
|
44 |
+
plt.xticks(rotation=0)
|
45 |
+
st.pyplot()
|
46 |
|
47 |
+
st.write("Number of poems for each age")
|
48 |
+
sns.catplot(x="age", data=df, kind="count")
|
49 |
+
plt.xticks(rotation=0)
|
50 |
+
st.pyplot()
|
51 |
|
52 |
+
st.write("Number of poems for each author")
|
53 |
+
sns.catplot(x="author", data=df, kind="count", aspect = 4)
|
54 |
+
plt.xticks(rotation=90)
|
55 |
+
st.pyplot()
|
56 |
|
57 |
# distributions of poem types according to ages and authors
|
58 |
+
st.write("Distributions of poem types according to ages and authors, \
|
59 |
+
seems that folks in renaissance loved the love themed poems \
|
60 |
+
and nature themed poems became popular later")
|
61 |
le = LabelEncoder()
|
62 |
|
63 |
df.author = le.fit_transform(df.author)
|
64 |
sns.catplot(x="age", y="author",hue="type", data=df)
|
65 |
st.pyplot()
|
66 |
|
67 |
+
|
68 |
+
#words = df.content.str.split(expand=True).unstack().value_counts()
|
69 |
# most appearing words other than stop words
|
70 |
+
words = df.content.str.split(expand=True).unstack().value_counts()
|
71 |
+
renaissance = df.content.loc[df.age == "Renaissance"].str.split(expand=True).unstack().value_counts()
|
72 |
+
modern = df.content.loc[df.age == "Modern"].str.split(expand=True).unstack().value_counts()
|
73 |
+
st.subheader("Visualizing content")
|
74 |
+
mask = np.array(Image.open(os.path.join(d, "poet.png")))
|
75 |
+
|
76 |
import matplotlib.pyplot as plt
|
77 |
def word_cloud(content, title):
|
78 |
wc = WordCloud(background_color="white", max_words=200,contour_width=3,
|
79 |
+
stopwords=STOPWORDS, max_font_size=50)
|
80 |
wc.generate(" ".join(content.index.values))
|
81 |
fig = plt.figure(figsize=(10, 10))
|
82 |
plt.title(title, fontsize=20)
|
|
|
84 |
plt.axis('off')
|
85 |
st.pyplot()
|
86 |
|
87 |
+
st.subheader("Most appearing words excluding stopwords in poems according to ages")
|
88 |
+
word_cloud(modern, "Word Cloud of Modern Poems")
|
89 |
+
|
90 |
+
word_cloud(renaissance, "Word Cloud Renaissance Poems")
|
91 |
+
|
92 |
+
# most appearing words including stopwords
|
93 |
+
st.write("Most appearing words including stopwords")
|
94 |
+
st.bar_chart(words[0:50])
|
95 |
+
st.set_option('deprecation.showPyplotGlobalUse', False)
|